Query Learning Model Research Articles

MODEL PEMBELAJARAN INKUIRI TERBIMBING DENGAN APLIKASI ZOOM UNTUK MENINGKATKAN PROSES DAN HASIL BELAJAR FISIKA MATERI LISTRIK DINAMIS

The guided investigation is a varied process and includes observing activities, formulating relevant questions, performing experiments, or experiments on students. Research on guided exploratory learning models with zoo applications to improve the process and learning outcomes of physical dynamic electrical material. This study aims to determine the Inkuri guided learning model with the Zoom application to improve the process and learning outcomes of dynamic electrical materials physics. This research was carried out on SMA N 1 Remboken in Class XII IPA 1 and XII IPA 2. This research method is experimental research. Research data based on post-test results. The average learning outcomes of students treated with the guided query learning model using the Zoom application was 64.966667 with a maximum score of 87 and a minimum score of 46. While the average learning outcomes of students who were treated with the Zoom application Application guided learning without guided inquiry were 58.48387097 with a maximum score of 78 and a minimum score of 44. From the data, the data normality test was performed, which showed Lcount <Ltable, which means that the experimental and control class data were normally distributed, then a hypothesis test was carried out. Data on student learning outcomes from the post-test. The results of the research by calculating the one-way T-test formula show that in the learning model for guided queries with the zoom application, the value of tcount = 2.9920534101 > ttable = 2.00099538 and then H0 is rejected. It can therefore be concluded that the average learning outcomes of the students using the guided inquiry learning model with the Zoom application are higher than the average learning outcomes of the students using the guided inquiry learning.

Circuit lower bounds from learning-theoretic approaches

An important open problem in computational complexity theory is to prove the size of circuits, namely, Boolean circuit lower bounds, necessary to solve explicit problems. We survey learning-theoretic approaches to proofs of Boolean circuit lower bounds in this paper. In particular, we discuss how to prove circuit lower bounds in uniform classes by assuming (or constructing) circuit-learning algorithms in several settings, such as the exact, probably approximately correct (PAC), and statistical query learning models.

On the teaching complexity of linear sets

Linear sets are the building blocks of semilinear sets, which are in turn closely connected to automata theory and formal languages. Prior work has investigated the learnability of linear sets and semilinear sets in three models – Valiant's PAC-learning model, Gold's learning in the limit model, and Angluin's query learning model. This paper considers teacher–learner models of learning families of linear sets, in which a benevolent teacher presents a set of labelled examples to the learner. First, we study the classical teaching model, in which a teacher must successfully teach any consistent learner. Second, we will apply a generalisation of the recently introduced recursive teaching model to several infinite classes of linear sets, and show that thus the maximum sample complexity of teaching these classes can be drastically reduced compared to classical teaching. To this end, a major focus of the paper will be on determining two relevant teaching parameters, the teaching dimension and recursive teaching dimension, for various families of linear sets.

An efficient distributed protein disorder prediction with pasted samples

In this paper, we compare prediction performance of a machine learning classifier constructed at once in memory with an ensemble of models constructed with the pasting procedure for protein disorder prediction. The pasting procedure takes sample bites of the training data as input, constructs a classification predictor on each sample and pastes the predictors together. This method has not been previously tested on protein structure data. With a sufficiently large sample size we observed increased performance for the pasting procedure compared with a single model constructed at once in memory for all window sizes. We attribute this increased performance to the robustness of the statistical query learning model. This procedure provides a means to improve classification performance at the protein disorder prediction task as well as construct models too large to be held at once in memory.

A complete characterization of statistical query learning with applications to evolvability

Statistical query (SQ) learning model of Kearns is a natural restriction of the PAC learning model in which a learning algorithm is allowed to obtain estimates of statistical properties of the examples but cannot see the examples themselves (Kearns, 1998 [29]). We describe a new and simple characterization of the query complexity of learning in the SQ learning model. Unlike the previously known bounds on SQ learning (Blum, et al., 1994; Bshouty and Feldman, 2002; Yang, 2005; Balcázar, et al., 2007; Simon, 2007 [9,11,42,3,37]) our characterization preserves the accuracy and the efficiency of learning. The preservation of accuracy implies that our characterization gives the first characterization of SQ learning in the agnostic learning framework of Haussler (1992) [23] and Kearns, Schapire and Sellie (1994) [31]. The preservation of efficiency is achieved using a new boosting technique and allows us to derive a new approach to the design of evolution algorithms in Valiantʼs model of evolvability (Valiant, 2009 [40]). We use this approach to demonstrate the existence of a large class of monotone evolution algorithms based on square loss performance estimation. These results differ significantly from the few known evolution algorithms and give evidence that evolvability in Valiantʼs model is a more versatile phenomenon than there had been previous reason to suspect.

Learning from positive and unlabeled examples

In many machine learning settings, labeled examples are difficult to collect while unlabeled data are abundant. Also, for some binary classification problems, positive examples which are elements of the target concept are available. Can these additional data be used to improve accuracy of supervised learning algorithms? We investigate in this paper the design of learning algorithms from positive and unlabeled data only. Many machine learning and data mining algorithms, such as decision tree induction algorithms and naive Bayes algorithms, use examples only to evaluate statistical queries (SQ-like algorithms). Kearns designed the statistical query learning model in order to describe these algorithms. Here, we design an algorithm scheme which transforms any SQ-like algorithm into an algorithm based on positive statistical queries (estimate for probabilities over the set of positive instances) and instance statistical queries (estimate for probabilities over the instance space). We prove that any class learnable in the statistical query learning model is learnable from positive statistical queries and instance statistical queries only if a lower bound on the weight of any target concept f can be estimated in polynomial time. Then, we design a decision tree induction algorithm POSC4.5, based on C4.5, that uses only positive and unlabeled examples and we give experimental results for this algorithm. In the case of imbalanced classes in the sense that one of the two classes (say the positive class) is heavily underrepresented compared to the other class, the learning problem remains open. This problem is challenging because it is encountered in many real-world applications.

New lower bounds for statistical query learning

We prove two lower bounds in the statistical query (SQ) learning model. The first lower bound is on weak-learning. We prove that for a concept class of SQ-dimension d, a running time of Ω ( d / log d ) is needed. The SQ-dimension of a concept class is defined to be the maximum number of concepts that are “uniformly correlated”, in that each of their pair has nearly the same correlation. This lower bound matches the upper bound in Blum et al. (Weakly Learning DNF and Characterizing Statistical Query Learning using Fourier Analysis, STOC 1994, pp. 253–262), up to a logarithmic factor. We prove this lower bound against an “honest SQ-oracle”, which gives a stronger result than the ones against the more frequently used “adversarial SQ-oracles”. The second lower bound is more general. It gives a continuous trade-off between the “advantage” of an algorithm in learning the target function and the number of queries it needs to make, where the advantage of an algorithm is the probability it succeeds in predicting a label minus the probability it does not. Both lower bounds extend and/or strengthen previous results, and solve an open problem left in previous papers. An earlier version of this paper [K. Yang, New lower bounds for statistical query learning, in: The Proceedings of the 15th Annual Conference on Computational Learning Theory, COLT 2002, Sydney, Australia, July 8–10, Lecture Notes in Computer Science, vol. 2375, 2002, pp. 229–243.] appeared in the proceedings of the 15th Annual Conference on Computational Learning Theory (COLT 2002).

Formal language identification: query learning vs. Gold-style learning

A natural approach towards powerful machine learning systems is to enable options for additional machine/user interactions, for instance by allowing the system to ask queries about the concept to be learned. This motivates the development and analysis of adequate formal learning models. In the present paper, we investigate two different types of query learning models in the context of learning indexable classes of recursive languages: Angluin's original model and a relaxation thereof, called learning with extra queries. In the original model the learner is restricted to query languages belonging to the target class, while in the new model it is allowed to query other languages, too. As usual, the following standard types of queries are considered: superset, subset, equivalence, and membership queries. The learning capabilities of the resulting query learning models are compared to one another and to different versions of Gold-style language learning from only positive data and from positive and negative data (including finite learning, conservative inference, and learning in the limit). A complete picture of the relation of all these models has been elaborated. A couple of interesting differences and similarities between query learning and Gold-style learning have been observed. In particular, query learning with extra superset queries coincides with conservative inference from only positive data. This result documents the naturalness of the new query model.

Learning elementary formal systems with queries

The elementary formal system ( EFS) is a kind of logic programs which directly manipulates strings, and the learnability of the subclass called hereditary EFSs ( HEFSs) has been investigated in the frameworks of the PAC-learning, query-learning, and inductive inference models. The hierarchy of HEFS is expressed by HEFS( m, k, t, r), where m, k, t and r denote the number of clauses, the occurrences of variables in the head, the number of atoms in the body, and the arity of predicate symbols. The present paper deals with the learnability of HEFS in the query learning model using equivalence queries and additional queries such as membership, predicate membership, entailment membership, and dependency queries. We show that the class HEFS(∗,k,t,r) is polynomial-time learnable with the equivalence and predicate membership queries and the class HEFS(∗,k,∗,r) with termination property is polynomial-time learnable with the equivalence, entailment membership, and dependency queries for the unbounded parameter ∗. A lowerbound on the number of queries is presented. We also show that the class HEFS(∗,k,t,r) is hard to learn with the equivalence and membership queries under the cryptographic assumptions. Furthermore, the learnability of the class of unions of regular pattern languages, which is a subclass of HEFSs, is investigated. The bounded unions of regular pattern languages are polynomial-time predictable with membership query. However, all unbounded unions of regular pattern languages are not polynomial-time predictable with membership queries if neither are the DNF formulas.

A New Abstract Combinatorial Dimension for Exact Learning via Queries

We introduce an abstract model of exact learning via queries that can be instantiated to all the query learning models currently in use, while being closer to them than previous unifying attempts. We present a characterization of those Boolean function classes learnable in this abstract model, in terms of a new combinatorial notion that we introduce, the abstract identification dimension. Then we prove that the particularization of our notion to specific known protocols such as equivalence, membership, and membership and equivalence queries results in exactly the same combinatorial notions currently known to characterize learning in these models, such as strong consistency dimension, extended teaching dimension, and certificate size. Our theory thus fully unifies all these characterizations. For models enjoying a specific property that we identify, the notion can be simplified while keeping the same characterizations. From our results we can derive combinatorial characterizations of all those other models for query learning proposed in the literature. We can also obtain the first polynomial-query learning algorithms for specific interesting problems such as learning DNF with proper subset and superset queries.

Learning orthogonal F-Horn formulas

In the PAC-learning, or the query learning model, it has been an important open problem to decide whether the class of DNF and CNF formulas is learnable. Recently, it was pointed out that the problem of PAC-learning for these classes with membership queries can be reduced to that of learning for the class of k-quasi Horn formulas with membership and equivalence queries. A k-quasi Horn formula is a CNF formula with each clause containing at most k unnegated literals. In this paper, notions of F-Horn formulas and l- F-Horn formulas, which are extensions of k-quasi formulas, are introduced, and it is shown that the problem of query learning for DNF and CNF formulas with membership and equivalence queries can be reduced to that for l- F-Horn formulas for an appropriate choice of F. It is shown that under a condition on F, the class of orthogonal F-Horn formulas is learnable with membership, equivalence and subset queries. Moreover, it is shown that under the same condition the class of orthogonal l- F-Horn formulas is learnable with membership and equivalence queries. For the latter result, the condition of orthogonality of F-Horn formulas is crucial because, if the statement held without the condition, then the result would imply that DNF and CNF are exactly learnable with membership and equivalence queries.

A Model of Interactive Teaching

Previous teaching models in the learning theory community have been batch models. That is, in these models the teacher has generated a single set of helpful examples to present to the learner. In this paper we present an interactive model in which the learner has the ability to ask queries as in the query learning model of Angluin. We show that this model is at least as powerful as previous teaching models. We also show that anything learnable with queries, even by a randomized learner, is teachable in our model. In all previous teaching models, all classes shown to be teachable are known to be efficiently learnable. An important concept class that is not known to be learnable is DNF formulas. We demonstrate the power of our approach by providing a deterministic teacher and learner for the class of DNF formulas. The learner makes only equivalence queries and all hypotheses are also DNF formulas.

Towards realistic theories of learning

In computational learning theory continuous efforts are made to formulate models of machine learning that are more realistic than previously available models. Two of the most popular models that have been recently proposed, Valiant’s PAC learning model and Angluin’s query learning model, can be thought of as refinements of preceding models such as Gold’s classic paradigm of identification in the limit, in which the question ofhow fast the learning can take place is emphasized. A considerable amount of results have been obtained within these two frameworks, resolving the learnability questions of many important classes of functions and languages. These two particular learning models are by no means comprehensive, and many important aspects of learning are not directly addressed in these models. Aiming towards more realistic theories of learning, many new models and extensions of existing learning models that attempt to formalize such aspects have been developed recently. In this paper, we will review some of these new extensions and models in computational learning theory, concentrating in particular on those proposed and studied by researchers at Theory NEC Laboratory RWCP, and their colleagues at other institutions.

The power of self-directed learning

This article studies self-directed learning, a variant of the on-line (or incremental) learning model in which the learner selects the presentation order for the instances. Alternatively, one can view this model as a variation of learning with membership queries in which the learner is only “charged” for membership queries for which it could not predict the outcome. We give tight bounds on the complexity of self-directed learning for the concept classes of monomials, monotone DNF formulas, and axis-parallel rectangles in {0, 1, ...,n − 1}d. These results demonstrate that the number of mistakes under self-directed learning can be surprisingly small. We then show that learning complexity in the model of self-directed learning is less than that of all other commonly studied on-line and query learning models. Next we explore the relationship between the complexity of self-directed learning and the Vapnik-Chervonenkis (VC-)dimension. We show that, in general, the VC-dimension and the self-directed learning complexity are incomparable. However, for some special cases, we show that the VC-dimension gives a lower bound for the self-directed learning complexity. Finally, we explore a relationship between Mitchell's version space algorithm and the existence of self-directed learning algorithms that make few mistakes.

The Power of Self-Directed Learning

This article studies self-directed learning, a variant of the on-line (or incremental) learning model in which the learner selects the presentation order for the instances. Alternatively, one can view this model as a variation of learning with membership queries in which the learner is only “charged” for membership queries for which it could not predict the outcome. We give tight bounds on the complexity of self-directed learning for the concept classes of monomials, monotone DNF formulas, and axis-parallel rectangles in {0, 1, \(\ldots \), n − 1}d. These results demonstrate that the number of mistakes under self-directed learning can be surprisingly small. We then show that learning complexity in the model of self-directed learning is less than that of all other commonly studied on-line and query learning models. Next we explore the relationship between the complexity of self-directed learning and the Vapnik-Chervonenkis (VC-)dimension. We show that, in general, the VC-dimension and the self-directed learning complexity are incomparable. However, for some special cases, we show that the VC-dimension gives a lower bound for the self-directed learning complexity. Finally, we explore a relationship between Mitchell's version space algorithm and the existence of self-directed learning algorithms that make few mistakes.